Comparison of Support Vector Machine (SVM) and Random Forest (RF) Algorithm Performance with Random Undersampling Technique to Predict Gestational Diabetes Mellitus Risk
Gestational Diabetes Mellitus (GDM) is a condition of glucose intolerance that develops during pregnancy until the birth process, which is characterized by an abnormal increase in blood sugar levels. Accurate early diagnosis is very important to provide information that can accelerate the treatment...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Politeknik Negeri Batam
2025-03-01
|
| Series: | Journal of Applied Informatics and Computing |
| Subjects: | |
| Online Access: | https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/9009 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849714235319255040 |
|---|---|
| author | Annisa Damayanti Anna Baita |
| author_facet | Annisa Damayanti Anna Baita |
| author_sort | Annisa Damayanti |
| collection | DOAJ |
| description | Gestational Diabetes Mellitus (GDM) is a condition of glucose intolerance that develops during pregnancy until the birth process, which is characterized by an abnormal increase in blood sugar levels. Accurate early diagnosis is very important to provide information that can accelerate the treatment process and reduce complications in the mother and baby. One of the machine learning methods that can be used to predict GDM is the Support Vector Machine (SVM) algorithm and the Random Forest (RF) algorithm. This study aims to compare, and evaluate GDM disease prediction models using the SVM and RF algorithms by balancing the target data using the Random Undersampling Technique. The approach using the random undersampling technique managed to increase accuracy by 18% from the accuracy before using the random undersampling technique. The SVM model in this study also uses hyperparameter tuning with kernel parameters, C (cost), and gamma, while the RF model uses Scoring Metrix and four other parameters, namely N_estimators, max_depth, min_samples_split, and min_samples_leaf. The best parameter search process is carried out using GridSearchCV on both models. The results of the study showed that the SVM classification model with random undersampling technique and hyperparameter tuning with K-Fold achieved an average accuracy of 100% with precision, recall, f1-score values also reaching 100%, with the Best Parameter Kernel Linear, C value = 0.1 and gamma value = 0.001 reaching the highest accuracy of 1.0, with a ROC-AUC value of 99% indicating very good prediction performance. While the RF model showed an accuracy result of 99%, tuning was also carried out using the appropriate parameters resulting in the same accuracy of 99%, with a ROC-AUC value of 99% as well. From both models, it shows that the SVM and RF algorithms have very good prediction performance in predicting DMG, but the SVM algorithm can predict DMG better than RF because the number of prediction errors is lower. |
| format | Article |
| id | doaj-art-68c6513bece0488f92fdc8c110cc9e96 |
| institution | DOAJ |
| issn | 2548-6861 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Politeknik Negeri Batam |
| record_format | Article |
| series | Journal of Applied Informatics and Computing |
| spelling | doaj-art-68c6513bece0488f92fdc8c110cc9e962025-08-20T03:13:45ZengPoliteknik Negeri BatamJournal of Applied Informatics and Computing2548-68612025-03-019232833710.30871/jaic.v9i2.90096589Comparison of Support Vector Machine (SVM) and Random Forest (RF) Algorithm Performance with Random Undersampling Technique to Predict Gestational Diabetes Mellitus RiskAnnisa Damayanti0Anna Baita1Universitas Amikom YogyakartaUniversitas Amikom YogyakartaGestational Diabetes Mellitus (GDM) is a condition of glucose intolerance that develops during pregnancy until the birth process, which is characterized by an abnormal increase in blood sugar levels. Accurate early diagnosis is very important to provide information that can accelerate the treatment process and reduce complications in the mother and baby. One of the machine learning methods that can be used to predict GDM is the Support Vector Machine (SVM) algorithm and the Random Forest (RF) algorithm. This study aims to compare, and evaluate GDM disease prediction models using the SVM and RF algorithms by balancing the target data using the Random Undersampling Technique. The approach using the random undersampling technique managed to increase accuracy by 18% from the accuracy before using the random undersampling technique. The SVM model in this study also uses hyperparameter tuning with kernel parameters, C (cost), and gamma, while the RF model uses Scoring Metrix and four other parameters, namely N_estimators, max_depth, min_samples_split, and min_samples_leaf. The best parameter search process is carried out using GridSearchCV on both models. The results of the study showed that the SVM classification model with random undersampling technique and hyperparameter tuning with K-Fold achieved an average accuracy of 100% with precision, recall, f1-score values also reaching 100%, with the Best Parameter Kernel Linear, C value = 0.1 and gamma value = 0.001 reaching the highest accuracy of 1.0, with a ROC-AUC value of 99% indicating very good prediction performance. While the RF model showed an accuracy result of 99%, tuning was also carried out using the appropriate parameters resulting in the same accuracy of 99%, with a ROC-AUC value of 99% as well. From both models, it shows that the SVM and RF algorithms have very good prediction performance in predicting DMG, but the SVM algorithm can predict DMG better than RF because the number of prediction errors is lower.https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/9009dmgprediksisvmundersampling |
| spellingShingle | Annisa Damayanti Anna Baita Comparison of Support Vector Machine (SVM) and Random Forest (RF) Algorithm Performance with Random Undersampling Technique to Predict Gestational Diabetes Mellitus Risk Journal of Applied Informatics and Computing dmg prediksi svm undersampling |
| title | Comparison of Support Vector Machine (SVM) and Random Forest (RF) Algorithm Performance with Random Undersampling Technique to Predict Gestational Diabetes Mellitus Risk |
| title_full | Comparison of Support Vector Machine (SVM) and Random Forest (RF) Algorithm Performance with Random Undersampling Technique to Predict Gestational Diabetes Mellitus Risk |
| title_fullStr | Comparison of Support Vector Machine (SVM) and Random Forest (RF) Algorithm Performance with Random Undersampling Technique to Predict Gestational Diabetes Mellitus Risk |
| title_full_unstemmed | Comparison of Support Vector Machine (SVM) and Random Forest (RF) Algorithm Performance with Random Undersampling Technique to Predict Gestational Diabetes Mellitus Risk |
| title_short | Comparison of Support Vector Machine (SVM) and Random Forest (RF) Algorithm Performance with Random Undersampling Technique to Predict Gestational Diabetes Mellitus Risk |
| title_sort | comparison of support vector machine svm and random forest rf algorithm performance with random undersampling technique to predict gestational diabetes mellitus risk |
| topic | dmg prediksi svm undersampling |
| url | https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/9009 |
| work_keys_str_mv | AT annisadamayanti comparisonofsupportvectormachinesvmandrandomforestrfalgorithmperformancewithrandomundersamplingtechniquetopredictgestationaldiabetesmellitusrisk AT annabaita comparisonofsupportvectormachinesvmandrandomforestrfalgorithmperformancewithrandomundersamplingtechniquetopredictgestationaldiabetesmellitusrisk |